Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
4.5
2.7
Journals
Applied Sciences
Special Issues
Deep Learning from Multi-Sourced Data
share announcement

Deep Learning from Multi-Sourced Data

A special issue of Applied Sciences (ISSN 2076-3417). This special issue belongs to the section "Computing and Artificial Intelligence".

Deadline for manuscript submissions: closed (31 May 2023) | Viewed by 11767

Special Issue Editors

Dr. Gaoang Wang

E-Mail Website
Guest Editor
International Campus, Zhejiang University, Haining, China
Interests: computer vision; machine learning; deep learning; video and image processing
Prof. Dr. Jenq-Neng Hwang

E-Mail Website
Guest Editor
Department of Electrical and Computer Engineering, University of Washington, Seattle, WA, USA
Interests: multimedia signal processing; pattern recognition; machine learning; multimedia networking; statistical pattern recognition

Special Issue Information

Dear Colleagues,

With the fast development of deep learning technologies, vast quantities of data are usually required for deep model training. It is worth employing complementary and rich information from multiple sourced datasets when a single dataset can not meet the demand. However, several challenges remain in the learning of multi-sourced data. Firstly, multi-sourced data can have different modalities. Combining information from multi-modality data is usually difficult. Secondly, label inconsistency is another major issue. Some data samples are annotated with fine labels, while some have weak labels or in some cases no labels. Thirdly, there are annotation biases among different annotators, resulting in noisy label problems. Fourthly, domain gaps usually exist in multi-sourced data. Despite these challenges, there is a high demand for practical applications related to multi-sourced data, such as federated learning, distributed learning, multi-sensor fusion techniques, etc. As a result, learning from multi-sourced data is garnering more and more attention. In this Special Issue, we welcome original research, applications, and review articles in all areas related to learning from multi-sourced data.

Dr. Gaoang Wang
Prof. Dr. Jenq-Neng Hwang
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Applied Sciences is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2400 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

  • multi-sourced learning
  • multi-modality fusion
  • federated learning
  • noisy label
  • doman adaptation

Published Papers (4 papers)

Download All Papers
Order results
Result details
Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:

Research

Jump to: Review

19 pages, 8934 KiB  
Article
Bionic Artificial Lateral Line Underwater Localization Based on the Neural Network Method
by Yanyun Pu, Zheyi Hang, Gaoang Wang and Huan Hu
Appl. Sci. 2022, 12(14), 7241; https://0-doi-org.brum.beds.ac.uk/10.3390/app12147241 - 18 Jul 2022
Cited by 5 | Viewed by 1746
Abstract
The lateral line system is an essential mechanosensory organ for organisms such as fish; it perceives the fluid environment in the near-field through the neuromasts on the lateral line system, supporting behaviors (e.g., obstacle avoidance and predation in fish). Inspired by the near-field [...] Read more.
The lateral line system is an essential mechanosensory organ for organisms such as fish; it perceives the fluid environment in the near-field through the neuromasts on the lateral line system, supporting behaviors (e.g., obstacle avoidance and predation in fish). Inspired by the near-field perception ability of fish, we propose an artificial lateral line system composed of pressure sensors that respond to a target’s relative position by measuring the pressure change of the target vibration near the lateral line. Based on the shortcomings of the idealized constrained modeling approach, a multilayer perceptron network was built in this paper to process the pressure signal and predict the coordinates on a two-dimensional plane. Previous studies primarily focused on the localization of a single dipole source and rarely considered the localization of multiple vibration sources. In this paper, we explore the localization of numerous dipole sources of the same and different frequency vibrations based on the prediction of the two-dimensional coordinates of double dipoles. The experimental results show that the mutual interference of two vibration sources causes an increase in the localization error. Compared with multiple sources of vibration at the same frequency, the positioning accuracies of various vibration sources at different frequencies are higher. In addition, we explored the effects of the number of sensors on the localization results. Full article
(This article belongs to the Special Issue Deep Learning from Multi-Sourced Data)
►▼ Show Figures

Figure 1

31 pages, 32120 KiB  
Article
The Impact of Personality and Demographic Variables in Collaborative Filtering of User Interest on Social Media
by Marwa M. Alrehili, Wael M. S. Yafooz, Abdullah Alsaeedi, Abdel-Hamid M. Emara, Aldosary Saad and Hussain Al Aqrabi
Appl. Sci. 2022, 12(4), 2157; https://0-doi-org.brum.beds.ac.uk/10.3390/app12042157 - 18 Feb 2022
Viewed by 2170
Abstract
The advent of social networks and micro-blogging sites online has led to an abundance of user-generated content. Hence, the enormous amount of content is viewed as inappropriate and unimportant information by many users on social media. Therefore, there is a need to use [...] Read more.
The advent of social networks and micro-blogging sites online has led to an abundance of user-generated content. Hence, the enormous amount of content is viewed as inappropriate and unimportant information by many users on social media. Therefore, there is a need to use personalization to select information related to users’ interests or searchers on social media platforms. Therefore, in recent years, user interest mining has been a prominent research area. However, almost all of the emerging research suffers from significant gaps and drawbacks. Firstly, it suffers from focusing on the explicit content of the users to determine the interests of the users while neglecting the multiple facts as the personality of the users; demographic data may be a valuable source of influence on the interests of the users. Secondly, existing work represents users with their interesting topics without considering the semantic similarity between the topics based on clusters to extract the users’ implicit interests. This paper is aims to propose a novel user interest mining approach and model based on demographic data, big five personality traits and similarity between the topics based on clusters. To demonstrate the leverage of combining user personality traits and demographic data into interest investigation, various experiments were conducted on the collected data. The experimental results showed that looking at personality and demographic data gives more accurate results in mining systems, increases utility, and can help address cold start problems for new users. Moreover, the results also showed that interesting topics were the dominant factor. On the other hand, the results showed that the current users’ implicit interests can be predicted through the cluster based on similar topics. Moreover, the hybrid model based on graphs facilitates the study of the patterns of interaction between users and topics. This model can be beneficial for researchers, people on social media, and for certain research in related fields. Full article
(This article belongs to the Special Issue Deep Learning from Multi-Sourced Data)
►▼ Show Figures

Figure 1

41 pages, 51639 KiB  
Article
An Interactive Scholarly Collaborative Network Based on Academic Relationships and Research Collaborations
by Abrar A. Almuhanna, Wael M. S. Yafooz and Abdullah Alsaeedi
Appl. Sci. 2022, 12(2), 915; https://0-doi-org.brum.beds.ac.uk/10.3390/app12020915 - 17 Jan 2022
Cited by 2 | Viewed by 2375
Abstract
In this era of digital transformation, when the amount of scholarly literature is rapidly growing, hundreds of papers are published online daily with regard to different fields, especially in relation to academic subjects. Therefore, it difficult to find an expert/author to collaborate with [...] Read more.
In this era of digital transformation, when the amount of scholarly literature is rapidly growing, hundreds of papers are published online daily with regard to different fields, especially in relation to academic subjects. Therefore, it difficult to find an expert/author to collaborate with from a specific research area. This is thought to be one of the most challenging activities in academia, and few people have considered authors’ multi-factors as an enhanced method to find potential collaborators or to identify the expert among them; consequently, this research aims to propose a novel model to improve the process of recommending authors. This is based on the authors’ similarity measurements by extracting their explicit and implicit topics of interest from their academic literature. The proposed model mainly consists of three factors: author-selected keywords, the extraction of a topic’s distribution from their publications, and their publication-based statistics. Furthermore, an enhanced approach for identifying expert authors by extracting evidence of expertise has been proposed based on the topic-modeling principle. Subsequently, an interactive network has been constructed that represents the predicted authors’ collaborative relationship, including the top-k potential collaborators for each individual. Three experiments have been conducted on the collected data; they demonstrated that the most influential factor for accurately recommending a collaborator was the topic’s distribution, which had an accuracy rate of 88.4%. Future work could involve building a heterogeneous co-collaboration network that includes both the authors with their affiliations and computing their similarities. In addition, the recommendations would be improved if potential and real collaborations were combined in a single network. Full article
(This article belongs to the Special Issue Deep Learning from Multi-Sourced Data)
►▼ Show Figures

Figure 1

Review

Jump to: Research

26 pages, 526 KiB  
Review
Deep Vision Multimodal Learning: Methodology, Benchmark, and Trend
by Wenhao Chai and Gaoang Wang
Appl. Sci. 2022, 12(13), 6588; https://0-doi-org.brum.beds.ac.uk/10.3390/app12136588 - 29 Jun 2022
Cited by 7 | Viewed by 4236
Abstract
Deep vision multimodal learning aims at combining deep visual representation learning with other modalities, such as text, sound, and data collected from other sensors. With the fast development of deep learning, vision multimodal learning has gained much interest from the community. This paper [...] Read more.
Deep vision multimodal learning aims at combining deep visual representation learning with other modalities, such as text, sound, and data collected from other sensors. With the fast development of deep learning, vision multimodal learning has gained much interest from the community. This paper reviews the types of architectures used in multimodal learning, including feature extraction, modality aggregation, and multimodal loss functions. Then, we discuss several learning paradigms such as supervised, semi-supervised, self-supervised, and transfer learning. We also introduce several practical challenges such as missing modalities and noisy modalities. Several applications and benchmarks on vision tasks are listed to help researchers gain a deeper understanding of progress in the field. Finally, we indicate that pretraining paradigm, unified multitask framework, missing and noisy modality, and multimodal task diversity could be the future trends and challenges in the deep vision multimodal learning field. Compared with existing surveys, this paper focuses on the most recent works and provides a thorough discussion of methodology, benchmarks, and future trends. Full article
(This article belongs to the Special Issue Deep Learning from Multi-Sourced Data)
►▼ Show Figures

Figure 1

Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:
 
Displaying articles 1-4
Back to TopTop